Deep Hough-Transform Line Priors

@article{Lin2020DeepHL,
  title={Deep Hough-Transform Line Priors},
  author={Yancong Lin and S. Pintea and J. V. Gemert},
  journal={ArXiv},
  year={2020},
  volume={abs/2007.09493}
}
Classical work on line segment detection is knowledge-based; it uses carefully designed geometric priors using either image gradients, pixel groupings, or Hough transform variants. Instead, current deep learning methods do away with all prior knowledge and replace priors by training deep networks on large manually annotated datasets. Here, we reduce the dependency on labeled data by building on the classic knowledge-based priors while using deep networks to learn features. We add line priors… Expand
Semi-supervised lane detection with Deep Hough Transform
TLDR
This work proposes a novel loss function exploiting geometric knowledge of lanes in Hough space, where a lane can be identified as a local maximum, and shows that the proposed Hough Transform loss improves performance significantly by learning from large amounts of unlabelled images. Expand
Fully Convolutional Line Parsing
TLDR
This work presents a one-stage Fully Convolutional Line Parsing network (F-Clip) that detects line segments from images and achieves a significantly better trade-off between efficiency and accuracy, resulting in a real-time line detector at up to 73 FPS on a single GPU. Expand
ChainLineNet: Deep-Learning-Based Segmentation and Parameterization of Chain Lines in Historical Prints
The paper structure of historical prints is sort of a unique fingerprint. Paper with the same origin shows similar chain line distances. As the manual measurement of chain line distances is timeExpand
ULSD: Unified Line Segment Detection across Pinhole, Fisheye, and Spherical Cameras
TLDR
Experimental results validate the superiority of the proposed ULSD to the SOTA methods both in accuracy and efficiency (40.6fps for pinhole images). Expand
Zero-Shot Domain Adaptation with a Physics Prior
TLDR
Improved performance for zero-shot day to night domain adaptation is demonstrated on both synthetic as well as natural datasets in various tasks, including classification, segmentation and place recognition. Expand
ELSD: Efficient Line Segment Detector and Descriptor
TLDR
The novel Efficient Line Segment Detector and Descriptor (ELSD) to simultaneously detect line segments and extract their descriptors in an image achieves the state-of-the-art performance on the Wireframe dataset and YorkUrban dataset, in both accuracy and efficiency. Expand
Zero-Shot Day-Night Domain Adaptation with a Physics Prior
We explore the zero-shot setting for day-night domain adaptation. The traditional domain adaptation setting is to train on one domain and adapt to the target domain by exploiting unlabeled dataExpand
A Deep Learning Approach Based on Graphs to Detect Plantation Lines
TLDR
A deep learning approach based on graphs to detect plantation lines in UAV-based RGB imagery presenting a challenging scenario containing spaced plants, which was compared against state-of-the-art deep learning methods and achieved superior performance. Expand
Harmonious Semantic Line Detection via Maximal Weight Clique Selection
TLDR
Experimental results demonstrate that the proposed algorithm can detect harmonious semantic lines effectively and efficiently and propose a novel metric, called HIoU, to assess the overall harmony of detected lines. Expand
SOLD2: Self-supervised Occlusion-aware Line Description and Detection
TLDR
This work introduces the first joint detection and description of line segments in a single deep network, which is highly discriminative, while remaining robust to viewpoint changes and occlusions. Expand
...
1
2
...

References

SHOWING 1-10 OF 57 REFERENCES
Connectivity-Enforcing Hough Transform for the Robust Extraction of Line Segments
TLDR
This work addresses the critical limitations of the HT as a line segment extractor by incorporating connectivity in the voting process, and produces a method that extracts the longest connected segments in each location of the image, thus also integrating into the HT voting process the usually separate step of individual segment extraction. Expand
A Deeply-Supervised Deconvolutional Network for Horizon Line Detection
TLDR
A novel approach for skyline detection is introduced, which adheres to a learning-based paradigm and exploits the representation power of deep architectures to improve the horizon line detection accuracy. Expand
Horizon Lines in the Wild
TLDR
This work introduces a large, realistic evaluation dataset, Horizon Lines in the Wild (HLW), containing natural images with labeled horizon lines, and investigates the application of convolutional neural networks for directly estimating the horizon line. Expand
Hyperpixel Flow: Semantic Correspondence With Multi-Layer Neural Features
TLDR
The proposed method, hyperpixel flow, sets a new state of the art on three standard benchmarks as well as a new dataset, SPair-71k, which contains a significantly larger number of image pairs than existing datasets, with more accurate and richer annotations for in-depth analysis. Expand
PPGNet: Learning Point-Pair Graph for Line Segment Detection
TLDR
This paper proposes to describe junctions, line segments and relationships between them with a simple graph, which is more structured and informative than end-point representation used in existing line segment detection methods and introduces the PPGNet, a convolutional neural network that directly infers a graph from an image. Expand
HoughNet: Neural Network Architecture for Vanishing Points Detection
TLDR
A novel neural network architecture based on Fast Hough Transform layer allows the neural network to accumulate features from linear areas across the entire image instead of local areas to solve the problem of vanishing points detection in the images of documents. Expand
Learning Attraction Field Representation for Robust Line Segment Detection
TLDR
A region-partition based attraction field dual representation for line segment maps, which poses the problem of line segment detection (LSD) as the region coloring problem and harnesses the best practices developed in ConvNets based semantic segmentation methods such as the encoder-decoder architecture and the a-trous convolution. Expand
MCMLSD: A Dynamic Programming Approach to Line Segment Detection
TLDR
A probabilistic algorithm that merges the advantages of both the Hough and Markov approaches to line segment detection and develops and applies a novel quantitative evaluation methodology that controls for under-and over-segmentation. Expand
Learning to Reconstruct 3D Manhattan Wireframes From a Single Image
TLDR
This work proposes a method to effectively exploit the global structural regularities for obtaining a compact, accurate, and intuitive 3D wireframe representation by trains a single convolutional neural network to simultaneously detect salient junctions and straight lines, as well as predict their 3D depth and vanishing points. Expand
Deep Hough Voting for 3D Object Detection in Point Clouds
TLDR
This work proposes VoteNet, an end-to-end 3D object detection network based on a synergy of deep point set networks and Hough voting that achieves state-of-the-art 3D detection on two large datasets of real 3D scans, ScanNet and SUN RGB-D with a simple design, compact model size and high efficiency. Expand
...
1
2
3
4
5
...